{"list":"other","total":74,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2206.02779","title":"Blended Latent Diffusion","created":"2022-06-06","cited_by_count":432},{"id":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412},{"id":"2304.03411","title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","created":"2023-04-06","cited_by_count":345},{"id":"2306.14435","title":"DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing","created":"2023-06-26","cited_by_count":294},{"id":"2305.17216","title":"Generating Images with Multimodal Language Models","created":"2023-05-26","cited_by_count":260},{"id":"2405.01434","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","created":"2024-05-02","cited_by_count":247},{"id":"2401.11708","title":"Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs","created":"2024-01-22","cited_by_count":224},{"id":"2305.10973","title":"Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold","created":"2023-05-18","cited_by_count":219},{"id":"2309.11497","title":"FreeU: Free Lunch in Diffusion U-Net","created":"2023-09-20","cited_by_count":196},{"id":"2307.02421","title":"DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models","created":"2023-07-05","cited_by_count":195},{"id":"2312.06739","title":"SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models","created":"2023-12-11","cited_by_count":177},{"id":"2309.15091","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","created":"2023-09-26","cited_by_count":141},{"id":"2407.05600","title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","created":"2024-07-08","cited_by_count":133},{"id":"2402.03286","title":"Training-Free Consistent Text-to-Image Generation","created":"2024-02-05","cited_by_count":125},{"id":"2311.16090","title":"Self-correcting LLM-controlled Diffusion Models","created":"2023-11-27","cited_by_count":113},{"id":"2402.02583","title":"DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing","created":"2024-02-04","cited_by_count":88},{"id":"2309.17444","title":"LLM-grounded Video Diffusion Models","created":"2023-09-29","cited_by_count":83},{"id":"1809.00812","title":"RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes","created":"2018-09-04","cited_by_count":74},{"id":"2308.04758","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","created":"2023-08-09","cited_by_count":72},{"id":"2312.08870","title":"Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens","created":"2023-12-12","cited_by_count":71},{"id":"2401.09414","title":"Vlogger: Make Your Dream A Vlog","created":"2024-01-17","cited_by_count":70},{"id":"2302.13153","title":"Directed Diffusion: Direct Control of Object Placement through Attention Guidance","created":"2023-02-25","cited_by_count":69},{"id":"2406.07547","title":"Zero-shot Image Editing with Reference Imitation","created":"2024-06-11","cited_by_count":65},{"id":"2403.14158","title":"Volumetric Environment Representation for Vision-Language Navigation","created":"2024-03-21","cited_by_count":63},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58},{"id":"2310.10640","title":"LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts","created":"2023-10-16","cited_by_count":54},{"id":"2403.13248","title":"Mora: Enabling Generalist Video Generation via A Multi-Agent Framework","created":"2024-03-20","cited_by_count":45},{"id":"2104.05845","title":"Visual Goal-Step Inference using wikiHow","created":"2021-04-12","cited_by_count":43},{"id":"2305.01795","title":"Multimodal Procedural Planning via Dual Text-Image Prompting","created":"2023-05-02","cited_by_count":40},{"id":"2312.07322","title":"GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos","created":"2023-12-12","cited_by_count":40},{"id":"2408.12957","title":"Image Segmentation in Foundation Model Era: A Survey","created":"2024-08-23","cited_by_count":35},{"id":"2402.00627","title":"CapHuman: Capture Your Moments in Parallel Universes","created":"2024-02-01","cited_by_count":22},{"id":"2407.15087","title":"Navigation Instruction Generation with BEV Perception and Large Language Models","created":"2024-07-21","cited_by_count":21},{"id":"2406.01388","title":"AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation","created":"2024-06-03","cited_by_count":20},{"id":"2208.12306","title":"Multimedia Generative Script Learning for Task Planning","created":"2022-08-25","cited_by_count":12},{"id":"2312.04552","title":"Generating Illustrated Instructions","created":"2023-12-07","cited_by_count":7},{"id":"2405.10122","title":"Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks","created":"2024-05-16","cited_by_count":6},{"id":"2406.04337","title":"Coherent Zero-Shot Visual Instruction Generation","created":"2024-06-06","cited_by_count":3}],"next_cursor":null}